Mapping natural language utterances to nodes in a knowledge graph
Active Publication Date: 2021-04-01
INTUIT INC
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Benefits of technology
The patent describes a method for mapping natural language to stored information using a natural language model and a knowledge engine. The user provides a natural language response to a set of topics and the model identifies a node of a knowledge graph based on the natural language response. The knowledge engine then provides a response to the user based on the identified node. The method also includes training the model using string data associated with a topic and using it to identify nodes in the knowledge graph. The technical effect of this invention is improved efficiency in identifying relevant information in response to user queries.
Problems solved by technology
Currently, no systems allow users to effectively search for technical information of a software application in their own words.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0014]Aspects of the present disclosure provide apparatuses, methods, processing systems, and computer readable mediums for mapping natural language utterances to knowledge graph data.
[0015]Generally, a provider of a software makes various sources of information about the software available to users, such as for customer support purposes. One such source of information may be a knowledge graph, a representational data structure used to store many types of data. For example, by tracking a user's progress through a particular software execution, a knowledge graph may be accessed to provide a quick-access answers at the user's point of progress. A knowledge graph typically includes a number of nodes, each corresponding to a particular data item or set of related data. Continuing the example above, a node may include data relating to a particular point of the software, including, but not limited to, a node identifier, a title of the query, and a response to the query.
[0016]In some cases...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
Certain aspects of the present disclosure provide techniques for mapping natural language to stored information. The method generally includes receiving a long-tail query comprising a natural language utterance from a user of an application associated with a set of topics and providing the natural language utterance to a natural language model configured to identify nodes of a knowledge graph. The method further includes, based on output of the natural language model, identifying a node of a knowledge graph associated with the natural language utterance, wherein the output of the natural language model includes a node identifier for the node of the knowledge graph and providing the node identifier to the knowledge engine. The method further includes receiving a response associated with the node of the knowledge graph from the knowledge engine and transmitting the response to the user in response to the long-tail query.
Description
[0001]Aspects of the present disclosure relate to mapping natural language information to non-natural language data.[0002]An important aspect of maintaining software applications for computing devices (or other types of services) is to provide customer support (such as technical help) to users. Commonly, material such as help guides, frequency asked questions (FAQ) documents or other compilations of technical information may be provided to assist users. In general, such material may be able to provide extensive information to some users, but only users knowledgeable enough about a particular software application may be able to effectively use such material. Currently, no systems allow users to effectively search for technical information of a software application in their own words. Thus, systems and methods are needed to map natural language of users to technical information of a software application.BRIEF SUMMARY[0003]Certain embodiments provide a method for mapping natural langua...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F16/332G06N5/02G06F17/27G10L15/06
CPCG06F16/3329G10L15/063G06F17/2785G06N5/02G06F40/284G06F40/30G06F40/216G06N5/022G06N20/00
Inventor OSMON, CYNTHIA J.MEIKE, ROGER C.KUMAR, SRICHARAN KALLUR PALLICOULOMBE, GREGORY KENNETHMALYNIN, PAVLO
Owner INTUIT INC